List your company

Reasoning on BIG-Bench Extra Hard

37.8ScoreQwen3-30B-A3B-Inst-2507
13.890420.097726.30532.5123Feb 9, 2026

Evaluation results

MethodLinks
Qwen3-30B-A3B-Inst-25072026.0237.81
LLaDA2.1-flashInference Mode=Q Mode2026.0235.773.17
LLaDA2.1-flashInference Mode=S Mode2026.0233.515.04
LLaDA2.0-flash2026.0227.864.6
Ling-flash-2.02026.0223.241
Qwen3-8Bno think=true2026.0218.27—
LLaDA2.0-mini2026.0216.472.03
LLaDA2.1-minimode=Q Mode2026.0215.781.66
LLaDA2.1-minimode=S Mode2026.0215.33.19
Ling-mini-2.02026.0214.81—